Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add CALLE-AI/awesome-phone-call-agents --skill call-politeness-strategy-auditorgit clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-politeness-strategy-auditor)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-politeness-strategy-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-politeness-strategy-auditor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-politeness-strategy-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-politeness-strategy-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.02095 |
| Opus 5.5 | $0.00029 | $0.00838 |
| Sonnet 5.5 | $0.00015 | $0.00419 |
| Haiku 4.5 | $0.00007 | $0.00210 |
Grade A, and why
call-politeness-strategy-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
call-politeness-strategy-auditor
Every data request is a small face-threatening act. Some agents pay the courtesy toll; some just grab.
Phone agents live on requests: date of birth, spelling, confirmations,
read-backs. Conversation-analytic politeness theory treats every such request
as a face-threatening act that speakers normally redress - a modal, a
"please", a hedge, an apology for the intrusion. A voice agent that fires
bare imperatives ("Give me your date of birth." "Spell your last name.")
gets the same data with more friction, and reads as a robot that grabs.
No sibling skill audits request phrasing: call-agent-certainty-calibrator
grades epistemic wording, call-leading-question-guard grades coercive
question form, call-data-minization-auditor grades whether the collection
was in goal scope. This skill grades the FORM of the ask - and only the
form: a polite request for out-of-scope data still fails the minimization
auditor.
When To Use
- after any collection or confirmation call, to review how the agent asked for what it needed - before reusing the goal template on the next campaign
- when iterating on goal wording to reduce caller friction and hang-ups
- alongside
call-data-minimization-auditor(scope) andcall-agent-certainty-calibrator(epistemics) for a full conduct pass
When Not To Use
- as a content-scope check - politeness never sanitizes WHAT is asked
(that is
call-data-minimization-auditor's object) - to judge sincerity, warmth, or cultural style; the markers are lexical and English-only, and directness norms vary across cultures
- as a rudeness verdict on humans - this grades the agent's request design
Verdicts
| Verdict | Meaning | Suggested routing |
|---|---|---|
COURTEOUS |
zero bald requests; every request carries >= 1 strategy marker | proceed; keep the card with the call record |
MIXED |
1-2 bald requests below the detection thresholds | review flagged turns; soften the goal template |
BALD_REQUESTS_DETECTED |
>= 3 bald requests, or a majority (with >= 3 requests) | rework the goal template before the next campaign |
NO_AGENT_REQUESTS |
no request sentences found (informational call) | nothing to grade |
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/example-call-result-bald.json 600 B
- references/example-call-result-mixed.json 695 B
- references/example-call-result-no-requests.json 630 B
- references/example-call-result.json 918 B
- references/example-goal.txt 348 B
- references/examples.md 5.3 KB
- references/safety.md 2.1 KB
- scripts/politeness_strategy_auditor.py 12 KB runs code
- scripts/test_politeness_strategy_auditor.py 14 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 136 lines · 73 tokens per session scan A 897159ab1a29
call-politeness-strategy-auditor is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 2,095 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-11.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…